LLMs
Build a Multi-agent Research Assistant With SwarmZero
Your own PerplexityAI (100% local).
Avi Chawla
367 posts published
Causal inference
Causality (Part 2)
A guide to building robust decision-making systems in businesses with causal inference.
LLMs
Run LLMs Locally with Ollama
A step-by-step hands-on guide.
RAG Systems Course
A Crash Course on Building RAG Systems – Part 2 (With Implementation)
A deep dive into evaluating RAG systems (with implementations).
RAG
A crash course on RAG systems - Part 2
Beginner-friendly and with implementation.
LLMs
Prompting vs. RAG vs. Fine-tuning
Which one is best for you?
Dimensionality Reduction
Avoid Using PCA for Visualization Unless...
...this plot says so.
LLMs
From PyTorch to Lightning Fabric
Scale model training with 4 small changes.
LLMs
Techniques to Extend Context Length of LLMs
Key techniques, explained in simple terms.
Machine Learning
KernelPCA vs. PCA
...and when to not use KernelPCA
RAG Systems Course
Foundations of RAG systems
A practical and beginner-friendly crash course on building RAG apps (with implementations).
Classical ML and Deep Learning
Causality (Part 1)
A guide to building robust decision-making systems in businesses with causal inference.
LLM and Fine-tuning
AugSBERT: Bi-encoders + Cross-encoders for Sentence Pair Similarity Scoring – Part 2
A deep dive into extensions of cross-encoders and bi-encoders for sentence pair similarity.
LLMs
5 Chunking Strategies For RAG
...explained in a single frame.
LLM and Fine-tuning
Bi-encoders and Cross-encoders for Sentence Pair Similarity Scoring (Part 1)
A deep dive into why BERT isn't effective for sentence similarity and advancements that shaped this task forever.
Classical ML and Deep Learning
Model Interpretability (Part 3)
A deep dive into interpretability methods, why they matter, along with their intuition, considerations, how to avoid being misled, and code.
PCA
Sparse Random Projections
An alternative to PCA for highly dimensional datasets.
Engineering Best Practices
5 Must-Know Ways to Test ML Models in Production (Implementation Included)
A beginner-friendly guide to model testing.
LLMs
NumPy Cheat Sheet for Data Scientists
40 most used methods.
Classical ML and Deep Learning
Model Interpretability (Part 2)
A deep dive into interpretability methods, why they matter, along with their intuition, considerations, how to avoid being misled, and code.
Machine Learning
Implementing a Siamese Network
A beginner-friendly implementation guide.
Machine Learning
Contrastive Learning Using Siamese Networks
Building a face unlock system.
Classical ML and Deep Learning
Model Interpretability (Part 1)
A deep dive into PDPs and ICE plots, along with their intuition, considerations, how to avoid being misled, and code.
37 min read
A Crash Course on Model Calibration
Modern neural networks being trained today are highly misleading. They appear to be heavily overconfident in their predictions. For instance, if a model predicts an event with a 70% probability, then ideally, out of 100 such predictions, approximately 70 should result in the event occurring. However, many experiments have revealed
56 min read
A Crash Course on Graph Neural Networks (With Implementation)
* Google Maps uses graph ML for ETA prediction. * Pinterest uses graph ML (PingSage) for recommendations. * Netflix uses graph ML (SemanticGNN) for recommendations. * Spotify uses graph ML (HGNNs) for audiobook recommendations. * Uber Eats uses graph ML (a GraphSAGE variant) to suggest dishes, restaurants, etc. The list could go on since almost
23 min read
Optimize ML Models to Run Them on Tiny Hardware using Quantization
Typically, the parameters of a neural network (layer weights) are represented using 32-bit floating-point numbers. The rationale is that since the parameters of an ML model are not constrained to any specific range of values, assigning a data type to parameters that cover a wide range of values is wise
Engineering Best Practices
Spark DataFrames and Big Data ML using PySpark on Databricks
A completely hands-on and beginner-friendly deep dive on PySpark using Databricks.
Pandas
Accelerate Pandas 20x using FireDucks
...by changing just one line of code.
Graph ML Course
Graph Neural Networks Part 3 (Implementation Included)
A practical and beginner-friendly guide to building neural networks on graph data.
Machine Learning
Knowledge Distillation with Teacher Assistant for Model Compression
A better and intuitive technique to model compression.
